In DQN, what is the real reason we don't backpropagate through the target network?
$begingroup$
Actually, if we are to backpropagate through the target network, there is no use for the target network anymore.
Let's say we don't use any target network. We hence enforce only the "temporal difference" allowing gradients to flow through both ways i.e. q(s,) and q(s',).
This completes the gradient and prevents known instabilities of DQN. While this training is much more stable, it is not widely used.
My question is why not? Where is the catch?
deep-learning reinforcement-learning
asked yesterday
PhizazPhizaz
61
New contributor
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
Actually, if we are to backpropagate through the target network, there is no use for the target network anymore.
Let's say we don't use any target network. We hence enforce only the "temporal difference" allowing gradients to flow through both ways i.e. q(s,) and q(s',).
This completes the gradient and prevents known instabilities of DQN. While this training is much more stable, it is not widely used.
My question is why not? Where is the catch?
deep-learning reinforcement-learning
asked yesterday
PhizazPhizaz
61
New contributor
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
Actually, if we are to backpropagate through the target network, there is no use for the target network anymore.
Let's say we don't use any target network. We hence enforce only the "temporal difference" allowing gradients to flow through both ways i.e. q(s,) and q(s',).
This completes the gradient and prevents known instabilities of DQN. While this training is much more stable, it is not widely used.
My question is why not? Where is the catch?
deep-learning reinforcement-learning
asked yesterday
PhizazPhizaz
61
New contributor
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
Actually, if we are to backpropagate through the target network, there is no use for the target network anymore.
Let's say we don't use any target network. We hence enforce only the "temporal difference" allowing gradients to flow through both ways i.e. q(s,) and q(s',).
This completes the gradient and prevents known instabilities of DQN. While this training is much more stable, it is not widely used.
My question is why not? Where is the catch?
deep-learning reinforcement-learning
deep-learning reinforcement-learning
asked yesterday
PhizazPhizaz
61
New contributor
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
PhizazPhizaz
61
New contributor
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
PhizazPhizaz
61
New contributor
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
PhizazPhizaz
61
asked yesterday
PhizazPhizaz
61
61
New contributor
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Phizaz is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Phizaz is a new contributor. Be nice, and check out our Code of Conduct.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44148%2fin-dqn-what-is-the-real-reason-we-dont-backpropagate-through-the-target-networ%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Phizaz is a new contributor. Be nice, and check out our Code of Conduct.
Phizaz is a new contributor. Be nice, and check out our Code of Conduct.
Phizaz is a new contributor. Be nice, and check out our Code of Conduct.
Phizaz is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44148%2fin-dqn-what-is-the-real-reason-we-dont-backpropagate-through-the-target-networ%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
